Claude Code Safety and Permission Mods

Stops every Bash git commit until the commit skill is opened

Route prompts, learn from edits, gate new mods and track costs inside Claude Code

Blocks secrets from memory saves, sessions, and RVF exports

Connect Claude Code to the ruflo swarm federation over signed Nostr messages

Stop destructive shell commands and ask Allow once or Deny before they run

Flags edits that store browser data in localStorage, tells the model to use a cookie

Guided modernization for any legacy codebase: start with /modernize, get an assessment, an interactive map, the business rules mined from the code…

.NET development plugin for Claude Code — Roslyn semantic analysis, DI/architecture/EF Core guards, convention-aware scaffolding, TDD agents…

Stops Claude from creating a new page whose target keyword an existing page already covers or ranks for (local pages + DataWise)

Manage Fly.io apps, Machines, volumes, secrets, Managed Postgres, and Sprites through the hosted Fly MCP server

Test-first workflow for coding agents, without the spec ceremony

Optional Claude Code 2.1.274 and 2.1.280 function hooks for Signet-eval policy and output redaction

The client for ultrapowers: /ultrapowers <plan-path> commits an approved plan and runs on an exe.dev fleet you provision — a disposable sandbox runs…

The issue-pipeline workflow system: standards heal, manager crew, guard hooks, and the workflow skills, for any repo

Flags accessibility misses as Claude writes UI: images without alt, unlabeled buttons, clickable divs

Sends Claude back when a reply ends on a yes/no question written as prose instead of AskUserQuestion

Anthropic의 blast-radius 샘플을 한글화하고 위험 명령 목록을 넓힌 k-mods 수정판

A Minecraft-inspired HUD for Claude Code: hearts for context, armor for safety nets, XP for verified work, and 60 advancements that persist across…

Live cost, context, and plan-quota meters above the Claude Code prompt (Nerd Font required for icons)

A debugger for Claude Code tool calls: breakpoints, pause/continue/reject/step, a timeline, an inspector, Error Lens failure diagnosis, a Permissions…

Ends a turn left on an open dialog (permission prompt, question) for 30 min by default and tells the agent the user is /afk; /dialog-timeout…

Looks up every new package before it installs: holds made-up names, typosquats, days-old releases and curl-into-shell for your answer, and lets the…

Claude Code, with receipts

Reversible redaction for Claude Code: private values are replaced with placeholders before the model API sees them and restored locally

Credential vault for Claude Code: macOS Keychain secrets, per-directory grants, injected env, redacted output, pane with import/export

Answers permission prompts for you: regex layers allow routine tool calls and always ask on pushes to protected branches, and haiku judges the rest…

Claude Code mods security layer: secret redaction, untrusted-content taint with a Rule-of-Two egress gate, skill inline-shell mediation guard, MCP…

Conan's Claude Code mods: caveman prompt, git-guard, dotenv-guard and an end-of-task sound, each toggled with /c-mods

Warns once before a message that will cost far more than usual: a large Claude Code context whose prompt cache has expired, or a model or effort…

Keeps AI coding agents inside your project's rules, from idea to merged code: spec design, lanes, layer rules, protected paths with an approval log…

An exoskeleton for Claude Code: guards against costly mistakes, a cockpit while working, a recap at the end and a few extras

The GTM operator mod for Claude Code: scores every go-to-market draft with its own skill pack's scorer, flags stale and inconsistent drafts across…

Holds risky shell commands (recursive deletes, git reset --hard, git clean, force pushes, discarded changes, migrations and third-party installs for…

J.A.R.V.I.S. HUD: arc-reactor spinner, live telemetry band (context, tok/s, agents by model), subagent uplink animations, input alerts, a…

5dive telemetry producer, seat panel, command surface and tool-call policy guard for Claude Code function hooks (early access)

Per-turn model routing for native Claude Code, with native tools and permissions preserved

Jev for coding agents: effort routing, output checks and GitHub reminders by default, with opt-in lockdown security gates

Holds prompts, @file contents and Read results that contain PII or secrets behind a review pane with per-type allow/redact decisions

At 90% of the 5-hour limit, tells the orchestrator and every subagent to checkpoint and stop at a safe point, then resumes them after the window…

Redacts secrets and PII from every row Claude Code stores, before the model reads it and before the transcript keeps it

Secure input window for API keys and passwords: Claude asks, you type into a masked field, the mod writes .env / GitHub Secrets itself

Revenantworks shroud mod for Claude Code 2.1.287+: masks secrets (its own shapes plus the gitleaks rule set), stream keys and, if you turn them on…

In-process guard for tamirs-superpowers: holds a destructive shell command (force push, rm -rf, git reset --hard, ...) until you answer Proceed or…

A live forecast of the context window above the prompt, with the 5-hour and 7-day usage windows, the session cost, today's spend and the subagent…

Command center for Claude Code: a live pane for your squad of subagents, limits and context, an orchestrator that fans work out to specialist agents…

Control VibeAudio from inside Claude Code: /vibeaudio opens a pane (mute, genre, volume, music, speech, banners, the share card, a setup check…

Vibeship: a 3D spaceship where your Claude Code agents work in crew uniforms